Instructions to use defog/sqlcoder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use defog/sqlcoder-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="defog/sqlcoder-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("defog/sqlcoder-7b") model = AutoModelForCausalLM.from_pretrained("defog/sqlcoder-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use defog/sqlcoder-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "defog/sqlcoder-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "defog/sqlcoder-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/defog/sqlcoder-7b
- SGLang
How to use defog/sqlcoder-7b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "defog/sqlcoder-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "defog/sqlcoder-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "defog/sqlcoder-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "defog/sqlcoder-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use defog/sqlcoder-7b with Docker Model Runner:
docker model run hf.co/defog/sqlcoder-7b
Great model but difficulty in generating MS SQL queries.
#3
by zabadugu - opened
Congratulations on great work! It really produces comparable (and superior) results to much larger models. However, I wasn't able to force it to generate queries in MS SQL syntax. I am using the same prompt style as mentioned in the colab notebook (just changed the schema and mentioned MS SQL database on the top), but it was still generating parts in Postgres syntax (for ex. using CURRENT_DATE). Are there any other ways to force the model